Detecting Pseudothrombocytopenia in the Era of Artificial Intelligence: Integration of Automated Hematology, Digital Morphology, and Expert Review.

Authors

Enoch Chi Ngai Lim, Nga Chong Lisa Cheng, Chi Eung Danforn Lim

Published in

Cureus. Volume 18. Issue 6. Pages e110690. Epub Jun 11, 2026.

Abstract

Pseudothrombocytopenia is an artefactual reduction in platelet count that occurs during laboratory testing, most commonly because ethylenediaminetetraacetic acid (EDTA) induces in vitro platelet aggregation. Although clinically benign, it may lead to unnecessary investigations, treatment, transfusion, referral, procedural delay, and patient anxiety when not recognised. Advances in hematology analyzers, including impedance, optical, fluorescence, digital morphology, and artificial intelligence (AI)-assisted technologies, offer opportunities to improve recognition of platelet aggregation and reduce reporting of artefactual thrombocytopenia. This narrative review summarises literature relating to pseudothrombocytopenia, automated platelet counting, digital morphology systems, and AI applications in hematology. Current evidence indicates that analyzer flags and platelet histograms provide useful screening signals but should not replace peripheral blood smear review. Optical and fluorescence platelet channels can improve platelet counting in selected EDTA-dependent samples, while digital morphology systems facilitate documentation of platelet aggregates and support platelet estimation. Emerging AI-assisted workflows are best understood as workflow-support tools that integrate analyzer data, sample timing, channel discordance, digital images, and expert review; they should not be treated as autonomous diagnostic systems. The strongest practical model combines automated platelet channels, digital morphology, AI-supported triage, clear report communication, and expert clinical oversight. Evidence remains heterogeneous, largely platform-specific, and limited by the lack of direct AI-versus-conventional workflow comparisons. Future research should validate integrated systems across diverse laboratory environments and assess clinically relevant outcomes, including diagnostic accuracy, false-positive and false-negative consequences, workflow efficiency, cost, and patient management.

PMID:
42438636
Bibliographic data and abstract were imported from PubMed on 13 Jul 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.